1. Self-supervised learning by cross-modal audio-video clustering;Alwassel;Advances in Neural Information Processing Systems,2020
2. Self-labelling via simultaneous clustering and representation learning;Asano,2019
3. Learning representations by maximizing mutual information across views;Bachman;Advances in neural information processing systems,2019
4. PsyNet: Self-Supervised Approach to Object Localization Using Point Symmetric Transformation
5. Self-Supervision By Prediction For Object Discovery In Videos